109 search results - page 1 / 22 » Interactive learning of mappings from visual percepts to act... |
ICML
2005
IEEE
14 years 5 months ago
2005
IEEE
We introduce flexible algorithms that can automatically learn mappings from images to actions by interacting with their environment. They work by introducing an image classifier i...
ECML
2006
Springer
13 years 8 months ago
2006
Springer
We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...
CONNECTION
2006
13 years 4 months ago
2006
This article describes a developmental system based on information theory implemented on a real robot that learns a model of its own sensory and actuator apparatus. There is no in...
ACCV
2010
Springer
12 years 11 months ago
2010
Springer
This work employs data mining algorithms to discover visual entities that are strongly associated to autonomously discovered modes of action, in an embodied agent. Mappings are lea...
ECML
2006
Springer
13 years 8 months ago
2006
Springer
Abstract. Approximate Policy Iteration (API) is a reinforcement learning paradigm that is able to solve high-dimensional, continuous control problems. We propose to exploit API for...